DEV Community

灯里/iku profile picture

灯里/iku

I find AI enjoyable. I write as a personal hobby. I am based in Japan. I manage with determination, passion, and some translation assistance.I would be delighted to collaborate on AI research, either

Joined Joined on 

Work

AI Engineer.

RAG Architecture Design Theory and Conceptual Organization in the Age of AI Agents: 7 Patterns
_768dd7ab130016ab8b0a profile

RAG Architecture Design Theory and Conceptual Organization in the Age of AI Agents: 7 Patterns

#rag #llm #architecture #agents
1
Comments
20 min read

Want to connect with 灯里/iku?

Create an account to connect with 灯里/iku. You can also sign in below to proceed if you already have an account.

Create Account
Already have an account? Sign in
LLMs Learn from "Pseudoscientific Papers" Too - Quality Control for AI Developers
_768dd7ab130016ab8b0a profile

LLMs Learn from "Pseudoscientific Papers" Too - Quality Control for AI Developers

#ai #machinelearning #llm #developers
5
Comments
9 min read
Analyzing the Best Diagramming Tools for the LLM Age Based on Token Efficiency
_768dd7ab130016ab8b0a profile

Analyzing the Best Diagramming Tools for the LLM Age Based on Token Efficiency

#mermaid #tokenefficiency #devops #llm
1
Comments
7 min read
AI Chatbot Developers: What's the "Other Safety" We Should Be Thinking About Now? User Protection.
_768dd7ab130016ab8b0a profile

AI Chatbot Developers: What's the "Other Safety" We Should Be Thinking About Now? User Protection.

#ai #security #llm #safety
5
Comments
24 min read
Google Opal is not a “degraded Dify”. Its strategic positioning and optimal utilisation methods revealed through actual use
_768dd7ab130016ab8b0a profile

Google Opal is not a “degraded Dify”. Its strategic positioning and optimal utilisation methods revealed through actual use

#ai #google #nocode #productivity
2
Comments
10 min read
"AI makes it cheaper, right?" - Is this happening in your country too?
_768dd7ab130016ab8b0a profile

"AI makes it cheaper, right?" - Is this happening in your country too?

1
Comments 1
3 min read
Beyond YAML: Logic Compression for 50%+ LLM Cost & Latency Reduction
_768dd7ab130016ab8b0a profile

Beyond YAML: Logic Compression for 50%+ LLM Cost & Latency Reduction

#promptengineering #llm #costreduction #tokenoptimization
Comments
18 min read
When Your CEO Says 'Let's Use AI': A Technology Selection Survival Guide
_768dd7ab130016ab8b0a profile

When Your CEO Says 'Let's Use AI': A Technology Selection Survival Guide

#ai #career #management
6
Comments
13 min read
The Era of Choosing RAG — Learning Cognitive Load and Architecture Design from GPT-5’s Failures
_768dd7ab130016ab8b0a profile

The Era of Choosing RAG — Learning Cognitive Load and Architecture Design from GPT-5’s Failures

#ai #rag #machinelearning #architecture
6
Comments
13 min read
loading...